Instructions to use fakezeta/Hermes-2-Pro-Llama-3-8B-ov-int8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fakezeta/Hermes-2-Pro-Llama-3-8B-ov-int8 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="fakezeta/Hermes-2-Pro-Llama-3-8B-ov-int8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fakezeta/Hermes-2-Pro-Llama-3-8B-ov-int8")
model = AutoModelForCausalLM.from_pretrained("fakezeta/Hermes-2-Pro-Llama-3-8B-ov-int8", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fakezeta/Hermes-2-Pro-Llama-3-8B-ov-int8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fakezeta/Hermes-2-Pro-Llama-3-8B-ov-int8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fakezeta/Hermes-2-Pro-Llama-3-8B-ov-int8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fakezeta/Hermes-2-Pro-Llama-3-8B-ov-int8

SGLang

How to use fakezeta/Hermes-2-Pro-Llama-3-8B-ov-int8 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "fakezeta/Hermes-2-Pro-Llama-3-8B-ov-int8" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fakezeta/Hermes-2-Pro-Llama-3-8B-ov-int8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "fakezeta/Hermes-2-Pro-Llama-3-8B-ov-int8" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fakezeta/Hermes-2-Pro-Llama-3-8B-ov-int8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use fakezeta/Hermes-2-Pro-Llama-3-8B-ov-int8 with Docker Model Runner:
```
docker model run hf.co/fakezeta/Hermes-2-Pro-Llama-3-8B-ov-int8
```

fakezeta commited on Jun 24, 2024

Commit

b90302f

verified ·

1 Parent(s): fddd869

Update README.md

Browse files

Add function calling configuration

Files changed (1) hide show

README.md +69 -1

README.md CHANGED Viewed

@@ -32,7 +32,7 @@ widget:
 # OpenVINO IR model with int8 quantization of Hermes-2-Pro-Llama-3-8B
 Model definition for LocalAI:
-```
 name: hermes-2-pro-llama3
 backend: transformers
 parameters:
@@ -43,6 +43,74 @@ template:
   use_tokenizer_template: true
 ```
 # Hermes 2 Pro - Llama-3 8B

 # OpenVINO IR model with int8 quantization of Hermes-2-Pro-Llama-3-8B
 Model definition for LocalAI:
+```yaml
 name: hermes-2-pro-llama3
 backend: transformers
 parameters:
   use_tokenizer_template: true
 ```
+LocalAI configuration for function calling
+```yaml
+name: hermes-2-pro-llama3
+backend: transformers
+parameters:
+  model: fakezeta/Hermes-2-Pro-Llama-3-8B-ov-int8
+context_size: 8192
+type: OVModelForCausalLM
+function:
+  # disable injecting the "answer" tool
+  disable_no_action: true
+  # This allows the grammar to also return messages
+  grammar_message: true
+  # Suffix to add to the grammar
+  grammar_prefix: '<tool_call>\n'
+  return_name_in_function_response: true
+  # Without grammar uncomment the lines below
+  # Warning: this is relying only on the capability of the
+  # LLM model to generate the correct function call.
+  # no_grammar: true
+  # json_regex_match: "(?s)<tool_call>(.*?)</tool_call>"
+  replace_results:
+    "<tool_call>": ""
+    "\'": "\""
+template:
+    chat_message: |
+      <|im_start|>{{if eq .RoleName "assistant"}}assistant{{else if eq .RoleName "system"}}system{{else if eq .RoleName "tool"}}tool{{else if eq .RoleName "user"}}user{{end}}
+      {{- if .FunctionCall }}
+      <tool_call>
+      {{- else if eq .RoleName "tool" }}
+      <tool_response>
+      {{- end }}
+      {{- if .Content}}
+      {{.Content }}
+      {{- end }}
+      {{- if .FunctionCall}}
+      {{toJson .FunctionCall}}
+      {{- end }}
+      {{- if .FunctionCall }}
+      </tool_call>
+      {{- else if eq .RoleName "tool" }}
+      </tool_response>
+      {{- end }}<|im_end|>
+    # https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B-GGUF#prompt-format-for-function-calling
+    function: |
+      <|im_start|>system
+      You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools:
+      <tools>
+      {{range .Functions}}
+      {'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }}
+      {{end}}
+      </tools>
+      Use the following pydantic model json schema for each tool call you will make:
+      {'title': 'FunctionCall', 'type': 'object', 'properties': {'arguments': {'title': 'Arguments', 'type': 'object'}, 'name': {'title': 'Name', 'type': 'string'}}, 'required': ['arguments', 'name']}
+      For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:
+      <tool_call>
+      {'arguments': <args-dict>, 'name': <function-name>}
+      </tool_call><|im_end|>
+      {{.Input -}}
+      <|im_start|>assistant
+      <tool_call>
+    chat: |
+      {{.Input -}}
+      <|im_start|>assistant
+    completion: |
+      {{.Input}}
+```
 # Hermes 2 Pro - Llama-3 8B